atlas
inf Inferentia
2 Generation 2
.
48xlarge 192 vCPU · 768 GiB

$16.88/hr

On-demand in Mumbai

192 vCPU

EPYC Milan, 2.95 GHz

768 GiB

4 GiB per vCPU

EBS only

Local storage

100 Gbps

Network bandwidth

60 Gbps

EBS bandwidth

x86_64

Architecture

Every way to pay

Prices in Mumbai. Bars are relative to on-demand.

PlanMonthlyYearlySaves

On-demand

Pay by the second, no commitment

$12,319$147,831

Reserved, 1 yr

No upfront, this size and region

$7,761$93,133−37%

Reserved, 3 yr

No upfront, this size and region

$5,731$68,775−53%

What will it cost me?

Enter how you plan to run it.

× inf2.48xlarge, on-demand

/mo

a year

You run these most of the time. A 1-year reservation bills every hour, and would still cost /mo.

Same usage on each planMonthlyYearly
On-demand
Reserved 1 yr
Reserved 3 yr

Reservations bill every hour of the month, whether the instance runs or not.

Other sizes in this family

Price roughly doubles with each step. Pick a size to open it.

Price in every region

Cheapest in US East (N. Virginia). Moving from Mumbai would save $34,115 a year per instance.

Not offered in N. California , Central , Calgary , Central , US-East , US-West , Zurich , Milan , Spain , Hyderabad , Jakarta , Melbourne , Malaysia , New Zealand , Thailand , Seoul , Osaka , Hong Kong , Taipei , UAE , Bahrain , Tel Aviv , Cape Town .

Specifications

API name
inf2.48xlarge
Processor
AMD EPYC 7R13 Processor
Local storage
EBS only
Family
Machine Learning ASIC Instances
Clock speed
2.95 GHz
Network
100 Gbps
Generation
Newest
Architecture
x86_64
EBS bandwidth
60 Gbps
vCPUs
192
Memory
768 GiB
GPUs
12 · 384 GB